Minimax Easy Vision Cli
OpenCode plugin that adds vision support for text-only models — paste images and the plugin analyzes them via a vision CLI tool (e.g., mmx vision describe)
33
18
2 in 7 days
38.3
Multi-signal model
1 month ago
2026-08-22
Install and configure
opencode.jsonWrites to this project's opencode.json — applies to this repository only.
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-minimax-easy-vision-cli@1.0.1"]
}Writes to ~/.config/opencode/opencode.json — applies to every project.
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-minimax-easy-vision-cli@1.0.1"]
}If you want to modify the plugin locally, install it into the project and reference the local path.
shell
pnpm add -D opencode-minimax-easy-vision-cliOpenCode loads npm dependencies through its embedded runtime on startup and caches them locally — no manual global install needed.
An OpenCode plugin that adds vision support to models that lack it. Paste images directly into the chat and ask questions, just like you would with Claude or GPT.
[!IMPORTANT]
Renamed from
opencode-minimax-easy-vision: Existing users only need to replace the old package name in thepluginarray withopencode-easy-vision. Existing plugin configuration continues to work; no other migration is required.
Table of Contents
- The Problem
- Demo
- Setup
- Usage
- Configuration
- Supported Image Formats
- Troubleshooting
- Uninstallation
- Contributing
- License
- References
The Problem
Many models, especially open-weight ones, have no vision capability. They are text-only and cannot process image input. For some models, such as MiniMax, an MCP tool can read an image through a vision service and return the analysis as text. The tool needs a local file path rather than a clipboard paste, so you would otherwise need to save each screenshot and provide its path yourself.
This plugin automates the entire workaround. It intercepts pasted images, saves them to disk, and injects the instructions the model needs to call the MCP tool with the correct path. You paste an image and ask a question. The plugin handles the rest.
Demo
| Without the plugin | With the plugin |
|---|---|
| The image is silently ignored by the model. | The model analyzes the attached image correctly before answering. |
https://github.com/user-attachments/assets/da7d8618-5de1-4a00-9250-a91493e3ea16
https://github.com/user-attachments/assets/fdb68339-b95b-46eb-90d4-ac2dbc0f436e
Setup
Manual Setup
1. Configure an MCP image analysis tool
The plugin works with any MCP server that can analyze an image from a local path or URL and return its analysis as text. Add one to your opencode.json.
Default: MiniMax Coding Plan MCP
{
"mcp": {
"MiniMax": {
"type": "local",
"command": ["uvx", "minimax-coding-plan-mcp"],
"environment": {
"MINIMAX_API_KEY": "your-api-key-here",
"MINIMAX_API_HOST": "https://api.minimax.io"
}
}
}
}
Alternative: openrouter-image-mcp
Routes image analysis through OpenRouter, giving you access to any vision-capable model including free ones.
{
"mcp": {
"openrouter_image": {
"type": "local",
"command": ["npx", "openrouter-image-mcp"],
"environment": {
"OPENROUTER_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
}
}
}
}
[!TIP]
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeis a free multimodal model designed for image perception and reasoning. Free model availability changes over time, so check OpenRouter's free models for current alternatives. Free endpoints use shared capacity and may respond more slowly or time out under load. When using this server, setimageAnalysisTooltoopenrouter_image_analyze_imagein the plugin config.
[!NOTE]
Any MCP server with an image analysis tool will work. The servers above are examples. For a different tool, set
imageAnalysisTool; see Configuration.
2. Install the plugin
With the OpenCode CLI (v1.3.4+):
Global (all projects):
opencode plugin opencode-easy-vision --global
Project-level (current directory only):
opencode plugin opencode-easy-vision
Or manually, add it to the plugin array in your opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-easy-vision"]
}
Agent-Assisted Setup
Paste this into OpenCode and let your agent handle the rest:
Set up opencode-easy-vision by following https://raw.githubusercontent.com/devadathanmb/opencode-easy-vision/main/AGENT_SETUP.md
What the agent will do
The agent follows the instructions in AGENT_SETUP.md. It will:
- Inspect your existing OpenCode and plugin configuration
- Ask whether to set up the plugin for all projects or only the current project
- Ask which MCP image analysis tool and models you want to use
- Update existing files in place instead of replacing them
- Summarize the changes and guide you through verification after a restart
Usage
- Select a configured model in OpenCode.
- Paste an image (
Cmd+V/Ctrl+V). - Ask your question, just like you would with Claude or GPT.
Configuration
[!IMPORTANT]
By default, this plugin only activates for MiniMax provider models, where MiniMax is the direct provider in OpenCode. These IDs match
minimax/*,minimax-cn/*, and related patterns. If you access a MiniMax model through a third-party provider such as OpenRouter, or use another model, add that model's pattern tomodels. See CONFIGURATION.md.
Each option uses the following priority order:
- Project level:
.opencode/opencode-easy-vision.json(or.jsonc) - User level:
~/.config/opencode/opencode-easy-vision.json(or.jsonc)
On first load, an example config is created at ~/.config/opencode/opencode-easy-vision.jsonc. See CONFIGURATION.md for config precedence, legacy config support, and the full option reference.
Supported Image Formats
PNG, JPEG, and WebP. Exact format support depends on the image analysis tool you configure.
Troubleshooting
Plugin not updating after a new release?
OpenCode caches plugins under ~/.cache/opencode/packages/. If it's still running an old version after a release, clear the cache entry and restart:
rm -rf ~/.cache/opencode/packages/opencode-easy-vision@latest
Plugin not activating?
By default, the plugin only activates for MiniMax provider models, with IDs matching minimax/*, minimax-cn/*, and related patterns. It does not activate for a MiniMax model accessed through OpenRouter or another provider. To use the plugin with a different model or provider, add the model's ID pattern to models in your config. See CONFIGURATION.md.
Uninstallation
Remove
opencode-easy-visionfrom thepluginarray in theopencode.jsonfile where you installed it.Delete the plugin config files you no longer need:
rm -f ~/.config/opencode/opencode-easy-vision.{json,jsonc}
rm -f .opencode/opencode-easy-vision.{json,jsonc}
If you migrated from opencode-minimax-easy-vision and no longer use it, you can also delete its legacy config files.
Contributing
See CONTRIBUTING.md for local development setup.
License
AGPL-3.0. See LICENSE.
References
Similar plugins
Easy Vision
opencode-easy-vision
OpenCode plugin that restores the paste-and-ask workflow for text-only models by saving pasted images and injecting MCP tool instructions
Ocm
@wntic/ocm
Plugin marketplace for opencode: install skills, agents, commands, JS plugins and MCP servers from any git repo — once, globally, kept up to date
Screenshot Vision
opencode-screenshot-vision
OpenCode plugin: let a text-only LLM read browser screenshots via local Ollama with OpenCode Zen fallback.